1 / 21

Thierry Worch, Anne Hasted & Hal MacFie

Open access and data processing of Social Media (Twitter) data – a new and valuable consumer research instrument. Thierry Worch, Anne Hasted & Hal MacFie. Overview. Using Twitter for Research – Macro vs Micro The R based macro TwitteR A food product application

demont
Télécharger la présentation

Thierry Worch, Anne Hasted & Hal MacFie

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Open access and data processing of Social Media (Twitter) data – a new and valuable consumer research instrument Thierry Worch, Anne Hasted &Hal MacFie

  2. Overview • Using Twitter for Research – Macro vs Micro • The R based macro TwitteR • A food product application • Possible use in Sensory and Consumer Science Slide 2

  3. Whatis Twitter? • Online social network and microblog. • Open text-based messages of up to 140 characters also known as “Tweets”. • Tweets are open: • personal information (what people are doing/feeling); • discussions; • sharing information... • Tweets are grouped together according to their content (use of “#word”). • People can “follow” friends, celebrities or brands to stay updated. • Over 500 million registered users in 2012, generating over 340 millions tweets/day, and handling over 1.6 billion search queries/day. Slide 3

  4. Diurnal and Seasonal Mood Vary with Work, Sleep, and Day length Across Diverse Cultures MACRO APPLICATION 1 • Study from Golder et al. • Science 30 September 2011: 1878-1881. • Previous studies small samples of American students. • Students are exposed to varying academic schedules that constrain when and how much they sleep. • Retrospective self-reports, vulnerable to memory error and experimenter demand effects. • Researchers have acknowledged the limitations of this methodology but have had no practical means for in situ real-time hourly observation of individual behavior in large and culturally diverse populations over many weeks. Slide 4

  5. Methodology 2.4 million individuals worldwide 509 million messages February 2008 and January 2010 Twitter data access Linguistic Inquiry and Word Count (LIWC) Analysis Negative Term Frequencies Positive Term Frequencies Time of day Time of day Slide 6

  6. Results • Individuals awaken in a good mood that deteriorates as the day progresses—which is consistent with the effects of sleep and circadian rhythm. • Seasonal change in baseline positive affect varies with change in day length. • People are happier on weekends, but the morning peak in positive affect is delayed by 2 hours, which suggests that people awaken later on weekends. Slide 7

  7. Effects of the Recession on Public Mood in the UK MACRO APPLICATION 2 • Landsdall-Welfare, Lampos, & Cristianini (University of Bristol, UK). • 484 million tweets 9.8 million UK users July 09 to Jan 12 Slide 7

  8. Results – 4 emotion categories Slide 8

  9. Micro Application 1: Airline companies • “R by example: mining Twitter for consumer attitudes towards airlines”, by Jeffrey Breen (June 2011) Slide 9

  10. Airline satisfaction scores • Retrieved from www.theacsi.org • Airlines do not score very high compared to other sectors. Slide 10

  11. Example of Tweets How can we access and summarize this data? Slide 11

  12. Searching tweets with twitteR Slide 12

  13. Game Plan for the Sentiment Analysis Slide 13

  14. Sentiment distributions Positive Negative Southwest United Airlines Southwest has much less negative tweets than United Airlines Slide 14

  15. Micro Application 2: ChocolateStudy • 5 chocolateproducts/brands: • Cadbury • Twix • Snickers • Hershey • KitKat • Once a week for 8 weeks. • 7000 tweets per brand. • Circlearound Manchester with a radius of 500 Miles. • English only • Duplicated tweets (and re-tweets) removed. Slide 15

  16. Sentiment Analysis Positive Negative Cadburys Kitkat Slide 16

  17. Classification of the termstweetedafter clean up using the R textmining routine TM 9 sensorydescriptors in the top 25 of eachproduct 5 sensorydescriptorsspecific to 2 or lessproducts Slide 17

  18. Results (chocolate occasion) CategoryTerms – 9 descriptors in the top 15 of eachproduct Unique Terms – 2 descriptorsspecific to 2 or lessproducts Slide 18

  19. Results (chocolate) • Cadbury have been running a competition and this is reflected in high frequency responses. • Can see descriptors that appear to define the category • Can observe product specific descriptors for sensory and occasion Slide 19

  20. Comments • Usage • TwitteRpackage "  easy "   to use ( once you know how) • Large numberof textsrequired – even for micro studies • Linguistic/Textprocessing software essential • Micro Applications - Sensory research • Vocabularydevelopment to define a category • Brand specificattributes • Change in sentiment over time and place • Research – Macro • find a stronghypothesisand the numberswill do the rest Slide 20

  21. Conclusion • Useful open accessresearch source • Methodologicalresearchneeded • Specialised sensory algorithmsneeded Slide 21

More Related